jobs

Senior Deep Learning Frameworks CUDA Software Engineer

NVIDIA is leading the way in groundbreaking developments in Artificial Intelligence, High Performance Computing and Visualization. The GPU, our invention, serves as the visual cortex of modern computers and is at the heart of our products a

In inglese

Company

NVIDIA

Location

US, CA, Santa Clara; US, TX, Austin; US, TX, Remote

Status

Open

Posted

2026-08-31T00:00:00+00:00

NVIDIA seeks a senior engineer to bring advanced CUDA features and distributed runtime technology into AI stacks such as PyTorch, JAX, TRT-LLM, vLLM, and SGLang. The role involves integrating CUDA features from proof-of-concept to production, analyzing AI workloads, improving the compiler-runtime interface, and designing fault-tolerant systems for multi-GPU training and inference. Requirements include a relevant degree, eight or more years of experience, and fluency in Python, C++, and CUDA. The team created core CUDA runtimes for deep learning and HPC; work ranges from 100K-GPU training to microsecond-latency inference.